Track D: NEXT BIG THING – Monday 24 April
13:15 – 14:00
Learn about the latest advances in speech recognition, speaker recognition event detection using deep learning, and other new techniques. This presentation demonstrates a system which takes any media and splits it into segments, labeling each segment with the corresponding speaker. It also transcribes what was said in the media, providing timestamps for each segment. Other advances include bird song recognition, recognition of cockpit commands, and more.
Presented by: Homayoon Beigi